wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

DailyRESTHelper now receives an aiohttp client session

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2024-08-01 18:08:57 -07:00
parent 8263d1dd6f
commit 4d9b7cdd61
51 changed files with 647 additions and 516 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/foundational/01-say-one-thing.py
View File

@@ -28,8 +28,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, _) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, _) = await configure(session)
transport = DailyTransport(
room_url, None, "Say One Thing", DailyParams(audio_out_enabled=True))

3
examples/foundational/02-llm-say-one-thing.py
View File

@@ -29,8 +29,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, _) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, _) = await configure(session)
transport = DailyTransport(
room_url,
None,

3
examples/foundational/03-still-frame.py
View File

@@ -28,8 +28,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, _) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, _) = await configure(session)
transport = DailyTransport(
room_url,
None,

3
examples/foundational/04-utterance-and-speech.py
View File

@@ -31,8 +31,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, _) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, _) = await configure(session)
transport = DailyTransport(room_url, None, "Static And Dynamic Speech")
meeting = TransportServiceOutput(transport, mic_enabled=True)

3
examples/foundational/05-sync-speech-and-image.py
View File

@@ -74,8 +74,9 @@ class MonthPrepender(FrameProcessor):
async def main():
(room_url, _) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, _) = await configure(session)
transport = DailyTransport(
room_url,
None,

3
examples/foundational/06-listen-and-respond.py
View File

@@ -35,8 +35,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

3
examples/foundational/06a-image-sync.py
View File

@@ -60,8 +60,9 @@ class ImageSyncAggregator(FrameProcessor):
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

4
examples/foundational/07-interruptible.py
View File

@@ -32,9 +32,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

3
examples/foundational/07a-interruptible-anthropic.py
View File

@@ -32,8 +32,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

3
examples/foundational/07b-interruptible-langchain.py
View File

@@ -48,8 +48,9 @@ def get_session_history(session_id: str) -> BaseChatMessageHistory:
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

3
examples/foundational/07c-interruptible-deepgram.py
View File

@@ -32,8 +32,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

95
examples/foundational/07d-interruptible-cartesia.py
View File

@@ -4,6 +4,7 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import os
import sys
@@ -32,62 +33,64 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_sample_rate=44100,
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_sample_rate=44100,
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
)
)
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="a0e99841-438c-4a64-b679-ae501e7d6091", # Barbershop Man
sample_rate=44100,
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="a0e99841-438c-4a64-b679-ae501e7d6091", # Barbershop Man
sample_rate=44100,
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
pipeline = Pipeline([
transport.input(), # Transport user input
tma_in, # User responses
llm, # LLM
tts, # TTS
tma_out, # Goes before the transport because cartesia has word-level timestamps!
transport.output(), # Transport bot output
])
pipeline = Pipeline([
transport.input(), # Transport user input
tma_in, # User responses
llm, # LLM
tts, # TTS
tma_out, # Goes before the transport because cartesia has word-level timestamps!
transport.output(), # Transport bot output
])
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
runner = PipelineRunner()
runner = PipelineRunner()
await runner.run(task)
await runner.run(task)
if __name__ == "__main__":

95
examples/foundational/07e-interruptible-playht.py
View File

@@ -4,6 +4,7 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import os
import sys
@@ -31,62 +32,64 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_enabled=True,
audio_out_sample_rate=16000,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_enabled=True,
audio_out_sample_rate=16000,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
)
)
)
tts = PlayHTTTSService(
user_id=os.getenv("PLAYHT_USER_ID"),
api_key=os.getenv("PLAYHT_API_KEY"),
voice_url="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json",
)
tts = PlayHTTTSService(
user_id=os.getenv("PLAYHT_USER_ID"),
api_key=os.getenv("PLAYHT_API_KEY"),
voice_url="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json",
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
pipeline = Pipeline([
transport.input(), # Transport user input
tma_in, # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
tma_out # Assistant spoken responses
])
pipeline = Pipeline([
transport.input(), # Transport user input
tma_in, # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
tma_out # Assistant spoken responses
])
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
runner = PipelineRunner()
runner = PipelineRunner()
await runner.run(task)
await runner.run(task)
if __name__ == "__main__":

107
examples/foundational/07f-interruptible-azure.py
View File

@@ -4,6 +4,7 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import os
import sys
@@ -31,69 +32,71 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_enabled=True,
audio_out_sample_rate=16000,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
vad_audio_passthrough=True,
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_enabled=True,
audio_out_sample_rate=16000,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
vad_audio_passthrough=True,
)
)
)
stt = AzureSTTService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"),
)
stt = AzureSTTService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"),
)
tts = AzureTTSService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"),
)
tts = AzureTTSService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"),
)
llm = AzureLLMService(
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
model=os.getenv("AZURE_CHATGPT_MODEL"),
)
llm = AzureLLMService(
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
model=os.getenv("AZURE_CHATGPT_MODEL"),
)
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
pipeline = Pipeline([
transport.input(), # Transport user input
stt, # STT
tma_in, # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
tma_out # Assistant spoken responses
])
pipeline = Pipeline([
transport.input(), # Transport user input
stt, # STT
tma_in, # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
tma_out # Assistant spoken responses
])
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
runner = PipelineRunner()
runner = PipelineRunner()
await runner.run(task)
await runner.run(task)
if __name__ == "__main__":

92
examples/foundational/07g-interruptible-openai-tts.py
View File

@@ -4,6 +4,7 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import os
import sys
@@ -31,62 +32,63 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_enabled=True,
audio_out_sample_rate=24000,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_enabled=True,
audio_out_sample_rate=24000,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
)
)
)
tts = OpenAITTSService(
api_key=os.getenv("OPENAI_API_KEY"),
voice="alloy"
)
tts = OpenAITTSService(
api_key=os.getenv("OPENAI_API_KEY"),
voice="alloy"
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
pipeline = Pipeline([
transport.input(), # Transport user input
tma_in, # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
tma_out # Assistant spoken responses
])
pipeline = Pipeline([
transport.input(), # Transport user input
tma_in, # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
tma_out # Assistant spoken responses
])
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
runner = PipelineRunner()
runner = PipelineRunner()
await runner.run(task)
await runner.run(task)
if __name__ == "__main__":

4
examples/foundational/07h-interruptible-openpipe.py
View File

@@ -35,9 +35,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

4
examples/foundational/07i-interruptible-xtts.py
View File

@@ -33,9 +33,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

4
examples/foundational/07j-interruptible-gladia.py
View File

@@ -34,9 +34,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

4
examples/foundational/08-bots-arguing.py
View File

@@ -23,9 +23,9 @@ logger.setLevel(logging.DEBUG)
async def main():
(room_url, _) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, _) = await configure(session)
transport = DailyTransport(
room_url,
None,

38
examples/foundational/09-mirror.py
View File

@@ -4,6 +4,7 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import sys
@@ -24,31 +25,32 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url, token, "Test",
DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
camera_out_enabled=True,
camera_out_is_live=True,
camera_out_width=1280,
camera_out_height=720
transport = DailyTransport(
room_url, token, "Test",
DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
camera_out_enabled=True,
camera_out_is_live=True,
camera_out_width=1280,
camera_out_height=720
)
)
)
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_video(participant["id"])
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_video(participant["id"])
pipeline = Pipeline([transport.input(), transport.output()])
pipeline = Pipeline([transport.input(), transport.output()])
runner = PipelineRunner()
runner = PipelineRunner()
task = PipelineTask(pipeline)
task = PipelineTask(pipeline)
await runner.run(task)
await runner.run(task)
if __name__ == "__main__":

52
examples/foundational/09a-local-mirror.py
View File

@@ -4,6 +4,7 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import sys
@@ -28,39 +29,42 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
tk_root = tk.Tk()
tk_root.title("Local Mirror")
tk_root = tk.Tk()
tk_root.title("Local Mirror")
daily_transport = DailyTransport(room_url, token, "Test", DailyParams(audio_in_enabled=True))
daily_transport = DailyTransport(
room_url, token, "Test", DailyParams(
audio_in_enabled=True))
tk_transport = TkLocalTransport(
tk_root,
TransportParams(
audio_out_enabled=True,
camera_out_enabled=True,
camera_out_is_live=True,
camera_out_width=1280,
camera_out_height=720))
tk_transport = TkLocalTransport(
tk_root,
TransportParams(
audio_out_enabled=True,
camera_out_enabled=True,
camera_out_is_live=True,
camera_out_width=1280,
camera_out_height=720))
@daily_transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_video(participant["id"])
@daily_transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_video(participant["id"])
pipeline = Pipeline([daily_transport.input(), tk_transport.output()])
pipeline = Pipeline([daily_transport.input(), tk_transport.output()])
task = PipelineTask(pipeline)
task = PipelineTask(pipeline)
async def run_tk():
while not task.has_finished():
tk_root.update()
tk_root.update_idletasks()
await asyncio.sleep(0.1)
async def run_tk():
while not task.has_finished():
tk_root.update()
tk_root.update_idletasks()
await asyncio.sleep(0.1)
runner = PipelineRunner()
runner = PipelineRunner()
await asyncio.gather(runner.run(task), run_tk())
await asyncio.gather(runner.run(task), run_tk())
if __name__ == "__main__":

4
examples/foundational/10-wake-phrase.py
View File

@@ -32,9 +32,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

4
examples/foundational/11-sound-effects.py
View File

@@ -84,9 +84,9 @@ class InboundSoundEffectWrapper(FrameProcessor):
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

4
examples/foundational/12-describe-video.py
View File

@@ -50,9 +50,9 @@ class UserImageRequester(FrameProcessor):
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

4
examples/foundational/12a-describe-video-gemini-flash.py
View File

@@ -50,9 +50,9 @@ class UserImageRequester(FrameProcessor):
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

4
examples/foundational/12b-describe-video-gpt-4o.py
View File

@@ -50,9 +50,9 @@ class UserImageRequester(FrameProcessor):
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

4
examples/foundational/12c-describe-video-anthropic.py
View File

@@ -50,9 +50,9 @@ class UserImageRequester(FrameProcessor):
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

20
examples/foundational/13-whisper-transcription.py
View File

@@ -4,6 +4,7 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import sys
@@ -36,22 +37,23 @@ class TranscriptionLogger(FrameProcessor):
async def main():
(room_url, _) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, _) = await configure(session)
transport = DailyTransport(room_url, None, "Transcription bot",
DailyParams(audio_in_enabled=True))
transport = DailyTransport(room_url, None, "Transcription bot",
DailyParams(audio_in_enabled=True))
stt = WhisperSTTService()
stt = WhisperSTTService()
tl = TranscriptionLogger()
tl = TranscriptionLogger()
pipeline = Pipeline([transport.input(), stt, tl])
pipeline = Pipeline([transport.input(), stt, tl])
task = PipelineTask(pipeline)
task = PipelineTask(pipeline)
runner = PipelineRunner()
runner = PipelineRunner()
await runner.run(task)
await runner.run(task)
if __name__ == "__main__":

20
examples/foundational/13b-deepgram-transcription.py
View File

@@ -4,6 +4,7 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import os
import sys
@@ -37,22 +38,23 @@ class TranscriptionLogger(FrameProcessor):
async def main():
(room_url, _) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, _) = await configure(session)
transport = DailyTransport(room_url, None, "Transcription bot",
DailyParams(audio_in_enabled=True))
transport = DailyTransport(room_url, None, "Transcription bot",
DailyParams(audio_in_enabled=True))
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tl = TranscriptionLogger()
tl = TranscriptionLogger()
pipeline = Pipeline([transport.input(), stt, tl])
pipeline = Pipeline([transport.input(), stt, tl])
task = PipelineTask(pipeline)
task = PipelineTask(pipeline)
runner = PipelineRunner()
runner = PipelineRunner()
await runner.run(task)
await runner.run(task)
if __name__ == "__main__":

4
examples/foundational/14-function-calling.py
View File

@@ -45,9 +45,9 @@ async def fetch_weather_from_api(llm, args):
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

156
examples/foundational/15-switch-voices.py
View File

@@ -4,6 +4,7 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import os
import sys
@@ -58,96 +59,97 @@ async def barbershop_man_filter(frame) -> bool:
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Pipecat",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
transport = DailyTransport(
room_url,
token,
"Pipecat",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
)
)
)
news_lady = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="bf991597-6c13-47e4-8411-91ec2de5c466", # Newslady
)
news_lady = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="bf991597-6c13-47e4-8411-91ec2de5c466", # Newslady
)
british_lady = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady
)
british_lady = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady
)
barbershop_man = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="a0e99841-438c-4a64-b679-ae501e7d6091", # Barbershop Man
)
barbershop_man = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="a0e99841-438c-4a64-b679-ae501e7d6091", # Barbershop Man
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
llm.register_function("switch_voice", switch_voice)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
llm.register_function("switch_voice", switch_voice)
tools = [
ChatCompletionToolParam(
type="function",
function={
"name": "switch_voice",
"description": "Switch your voice only when the user asks you to",
"parameters": {
"type": "object",
"properties": {
"voice": {
"type": "string",
"description": "The voice the user wants you to use",
tools = [
ChatCompletionToolParam(
type="function",
function={
"name": "switch_voice",
"description": "Switch your voice only when the user asks you to",
"parameters": {
"type": "object",
"properties": {
"voice": {
"type": "string",
"description": "The voice the user wants you to use",
},
},
"required": ["voice"],
},
"required": ["voice"],
},
})]
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities. Respond to what the user said in a creative and helpful way. Your output should not include non-alphanumeric characters. You can do the following voices: 'News Lady', 'British Lady' and 'Barbershop Man'.",
},
]
context = OpenAILLMContext(messages, tools)
tma_in = LLMUserContextAggregator(context)
tma_out = LLMAssistantContextAggregator(context)
pipeline = Pipeline([
transport.input(), # Transport user input
tma_in, # User responses
llm, # LLM
ParallelPipeline( # TTS (one of the following vocies)
[FunctionFilter(news_lady_filter), news_lady], # News Lady voice
[FunctionFilter(british_lady_filter), british_lady], # British Lady voice
[FunctionFilter(barbershop_man_filter), barbershop_man], # Barbershop Man voice
),
transport.output(), # Transport bot output
tma_out # Assistant spoken responses
])
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
})]
messages = [
{
"role": "system",
"content": f"Please introduce yourself to the user and let them know the voices you can do. Your initial responses should be as if you were a {current_voice}."})
await task.queue_frames([LLMMessagesFrame(messages)])
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities. Respond to what the user said in a creative and helpful way. Your output should not include non-alphanumeric characters. You can do the following voices: 'News Lady', 'British Lady' and 'Barbershop Man'.",
},
]
runner = PipelineRunner()
context = OpenAILLMContext(messages, tools)
tma_in = LLMUserContextAggregator(context)
tma_out = LLMAssistantContextAggregator(context)
await runner.run(task)
pipeline = Pipeline([
transport.input(), # Transport user input
tma_in, # User responses
llm, # LLM
ParallelPipeline( # TTS (one of the following vocies)
[FunctionFilter(news_lady_filter), news_lady], # News Lady voice
[FunctionFilter(british_lady_filter), british_lady], # British Lady voice
[FunctionFilter(barbershop_man_filter), barbershop_man], # Barbershop Man voice
),
transport.output(), # Transport bot output
tma_out # Assistant spoken responses
])
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append(
{
"role": "system",
"content": f"Please introduce yourself to the user and let them know the voices you can do. Your initial responses should be as if you were a {current_voice}."})
await task.queue_frames([LLMMessagesFrame(messages)])
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":

4
examples/foundational/15a-switch-languages.py
View File

@@ -56,9 +56,9 @@ async def spanish_filter(frame) -> bool:
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

5
examples/foundational/16-gpu-container-local-bot.py
View File

@@ -8,7 +8,6 @@ import asyncio
import aiohttp
import os
import sys
import json
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
@@ -33,9 +32,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

4
examples/foundational/17-detect-user-idle.py
View File

@@ -34,9 +34,9 @@ logger.add(sys.stderr, level="DEBUG")
async def main():
(room_url, token) = await configure()
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,

8
examples/foundational/runner.py
View File

@@ -4,13 +4,14 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import argparse
import os
from pipecat.transports.services.helpers.daily_rest import DailyRESTHelper
async def configure():
async def configure(aiohttp_session: aiohttp.ClientSession):
parser = argparse.ArgumentParser(description="Daily AI SDK Bot Sample")
parser.add_argument(
"-u",
@@ -38,7 +39,10 @@ async def configure():
if not key:
raise Exception("No Daily API key specified. use the -k/--apikey option from the command line, or set DAILY_API_KEY in your environment to specify a Daily API key, available from https://dashboard.daily.co/developers.")
daily_rest_helper = DailyRESTHelper(key, os.getenv("DAILY_API_URL", "https://api.daily.co/v1"))
daily_rest_helper = DailyRESTHelper(
daily_api_key=key,
daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
aiohttp_session=aiohttp_session)
# Create a meeting token for the given room with an expiration 1 hour in
# the future.